Mercurial > repos > mingchen0919 > rmarkdown_bdss_client

changeset 21:a709a705ce09 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/statonlab/docker-GRReport/tree/master/my_tools/rmarkdown_bdss_client commit 813dcaa22f297814dd6d6a8c4c5ff01664942aa6-dirty
author mingchen0919
date Sat, 14 Oct 2017 19:54:57 -0400
parents 531c00a2acbf
children 89cc5b026494
files bdss_client.Rmd bdss_client.xml bdss_client_sra.Rmd bdss_client_sra.xml bdss_client_sra_pe.Rmd bdss_client_sra_pe.xml bdss_client_sra_pe_render.R bdss_client_sra_render.R bdss_client_sra_se.Rmd bdss_client_sra_se.xml bdss_client_sra_se_render.R
diffstat 11 files changed, 243 insertions(+), 488 deletions(-) [+]
line wrap: on
line diff
--- a/bdss_client.Rmd	Sat Oct 14 17:15:39 2017 -0400
+++ b/bdss_client.Rmd	Sat Oct 14 19:54:57 2017 -0400
@@ -10,7 +10,8 @@
 
 ```{r setup, include=FALSE, warning=FALSE, message=FALSE}
 knitr::opts_chunk$set(
-  echo = ECHO
+  echo = ECHO,
+  error=TRUE
 )
 ```
 
@@ -39,9 +40,13 @@
 urls = urls[urls != '']
 # loop through SRA accessions to download and extract reads.
 for(url in urls) {
+    print(url)
     bdss_command = paste0('/tool_deps/_conda/bin/bdss transfer --destination read_files_directory -u ', url)
+    print(bdss_command)
     print(system(bdss_command, intern = TRUE))
 }
+# all files that need to be saved should be moved to REPORT_DIR directory
+# print(system('mv read_files_directory REPORT_DIR', intern = TRUE))
 ```
 
 
--- a/bdss_client.xml	Sat Oct 14 17:15:39 2017 -0400
+++ b/bdss_client.xml	Sat Oct 14 19:54:57 2017 -0400
@@ -1,4 +1,4 @@
-<tool id="rmarkdown_bdss_client" name="BDSS client" version="1.0.1">
+<tool id="rmarkdown_bdss_client" name="BDSS client" version="1.0.2">
     <requirements>
         <requirement type="package" version="1.15.0.6-0">pandoc</requirement>
         <requirement type="package" version="3.3.2">r-base</requirement>
@@ -38,9 +38,9 @@
                label="Display analysis code in report?"/>
     </inputs>
     <outputs>
-        <data format="html" name="report" label="BDSS report"/>
-        <data name="output">
-            <discover_datasets pattern="__name_and_ext__" directory="read_files_directory"/>
+        <data format="html" name="report" label="BDSS client report"/>
+        <data name="output" label="BDSS downloaded data">
+            <discover_datasets pattern="__name_and_ext__" directory="read_files_directory" visible="true"/>
         </data>
         <data format="txt" name="sink_message" label="Warnings and Errors" from_work_dir="warnings_and_errors.txt"/>
     </outputs>
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/bdss_client_sra.Rmd	Sat Oct 14 19:54:57 2017 -0400
@@ -0,0 +1,86 @@
+---
+title: 'Download and extract single end fastq/fasta data with BDSS client from SRA accessions'
+output:
+    html_document:
+      number_sections: true
+      toc: true
+      theme: cosmo
+      highlight: tango
+---
+
+```{r setup, include=FALSE, warning=FALSE, message=FALSE}
+knitr::opts_chunk$set(
+  echo = ECHO,
+  error=TRUE
+)
+```
+
+# Command line arguments
+
+```{r 'command line arguments'}
+str(opt)
+```
+
+# BDSS configuration file
+
+First, we create a bdss configuration file `bdss.cfg` in the current directory.
+
+```{r}
+system('echo "[metadata_repository]" > bdss.cfg')
+system('echo url=http://bdss.bioinfo.wsu.edu/ >> bdss.cfg')
+```
+
+# Download and extract reads
+
+```{r 'download and extract reads'}
+# create two directories, one for single end and the other for paired end SRA reads.
+dir.create('se_read_files_directory')
+dir.create('pe_read_files_directory')
+# download and extract reads (single end)
+sra_ids_se = strsplit(gsub(',', ' ', 'SRA_IDS_SE'), ' ')[[1]]
+sra_ids_se = sra_ids[sra_ids != '']
+# loop through SRA accessions to download and extract reads.
+for(id in sra_ids) {
+    # build URL from SRA id
+    url = paste0('ftp://ftp.ncbi.nlm.nih.gov/sra/sra-instant/reads/ByRun/sra/',
+                 substr(id, 1, 3), '/',
+                 substr(id, 1, 6), '/', id, '/', id, '.sra')
+    # download sra file with bdss
+    bdss_command = paste0('/tool_deps/_conda/bin/bdss transfer -u ', url)
+    system(bdss_command, intern = TRUE)
+    # convert .sra to .fastq/.fasta
+    if('FORMAT' == 'fasta') {
+      command = paste0('fastq-dump --fasta -O read_files_directory ', id)
+    } else {
+      command = paste0('fastq-dump -O read_files_directory ', id)
+    }
+}
+
+# download and extract reads (paired end)
+sra_ids_pe = strsplit(gsub(',', ' ', 'SRA_IDS_PE'), ' ')[[1]]
+sra_ids_pe = sra_ids[sra_ids != '']
+# loop through SRA accessions to download and extract reads.
+for(id in sra_ids) {
+    # build URL from SRA id
+    url = paste0('ftp://ftp.ncbi.nlm.nih.gov/sra/sra-instant/reads/ByRun/sra/',
+                 substr(id, 1, 3), '/',
+                 substr(id, 1, 6), '/', id, '/', id, '.sra')
+    # download sra file with bdss
+    bdss_command = paste0('/tool_deps/_conda/bin/bdss transfer -u ', url)
+    system(bdss_command, intern = TRUE)
+    # convert .sra to .fastq/.fasta
+    if('FORMAT' == 'fasta') {
+      command = paste0('fastq-dump --fasta --split-files -O pe_read_files_directory ', id)
+    } else {
+      command = paste0('fastq-dump --split-files -O pe_read_files_directory ', id)
+    }
+}
+
+# rename files for paired end reads
+old_files = paste0('./read_files_directory/', list.files('./read_files_directory'))
+new_files = gsub('_1', '_forward', old_files)
+new_files = gsub('_2', '_reverse', new_files)
+file.rename(old_files, new_files)
+```
+
+
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/bdss_client_sra.xml	Sat Oct 14 19:54:57 2017 -0400
@@ -0,0 +1,58 @@
+<tool id="rmarkdown_bdss_client_sra" name="BDSS client SRA" version="1.0.2">
+    <requirements>
+        <requirement type="package" version="1.15.0.6-0">pandoc</requirement>
+        <requirement type="package" version="3.3.2">r-base</requirement>
+        <requirement type="package" version="1.20.0">r-getopt</requirement>
+        <requirement type="package" version="1.2">r-rmarkdown</requirement>
+        <requirement type="package" version="0.3.5">r-htmltools</requirement>
+        <requirement type="package" version="0.5.0">r-dplyr</requirement>
+        <requirement type="package" version="0.5.4">parallel-fastq-dump</requirement>
+        <requirement type="package" version="1.95_4.8">r-rcurl</requirement>
+    </requirements>
+    <description>
+        Download data with BDSS client and generate list (single end SRA data) and list:paired dataset collection (paired end SRA data).
+    </description>
+    <stdio>
+        <!--All stderr are redirected to a file. "XXX" is used to match with nothing-->
+        <regex match="XXX"
+               source="stderr"
+               level="warning"
+               description="Check the warnings_and_errors.txt file for more details."/>
+    </stdio>
+    <command>
+        <![CDATA[
+            Rscript '${__tool_directory__}/bdss_client_sra_render.R'
+                -i '$sra_ids_se'
+                -p '$sra_ids_pe'
+                -e $echo
+
+                -r $report
+                -d $report.files_path
+                -s $sink_message
+
+                -t '${__tool_directory__}/bdss_client_sra.Rmd'
+        ]]>
+    </command>
+    <inputs>
+        <param type="text" name="sra_ids_se" area="true" size="5x25" label="SRR/DRR/ERR accessions of single end SRA" optional="false"
+               help="A list of SRR/DRR/ERR accessions separated by comma or space. e.g. SRR6077558,ERR343809"/>
+        <param type="text" name="sra_ids_pe" area="true" size="5x25" label="SRR/DRR/ERR accessions of paired end SRA" optional="false"
+               help="A list of SRR/DRR/ERR accessions separated by comma or space. e.g. ERR2105526"/>
+        <param type="boolean" name="format" truevalue="fastq" falsevalue="fasta" checked="true"
+               label="output files in fastq (Yes) or fasta (No)?"/>
+        <param type="boolean" name="echo" truevalue="TRUE" falsevalue="FALSE" checked="false"
+               label="Display analysis code in report?"/>
+    </inputs>
+    <outputs>
+        <data format="html" name="report" label="BDSS client report"/>
+        <!--list dataset collection for single end SRA data-->
+        <collection type="list" name="list_collection" label="Fastq-dump (single end reads)">
+            <discover_datasets pattern="__name_and_ext__" directory="read_files_directory" />
+        </collection>
+        <!--list:paired dataset collection for paired end SRA data-->
+        <collection type="list:paired" name="list_collection" label="Fastq-dump (paired end reads)">
+            <discover_datasets pattern="(?P&lt;identifier_0&gt;[^_]+)_(?P&lt;identifier_1&gt;[^_]+)\.(?P&lt;ext&gt;[^\._]+)?" directory="read_files_directory"/>
+        </collection>
+        <data format="txt" name="sink_message" label="Warnings and Errors" from_work_dir="warnings_and_errors.txt"/>
+    </outputs>
+</tool>
\ No newline at end of file
--- a/bdss_client_sra_pe.Rmd	Sat Oct 14 17:15:39 2017 -0400
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,92 +0,0 @@
----
-title: 'Download and extract paired end fastq/fasta data with BDSS client from SRA accessions'
-output:
-    html_document:
-      number_sections: true
-      toc: true
-      theme: cosmo
-      highlight: tango
----
-
-```{r setup, include=FALSE, warning=FALSE, message=FALSE}
-knitr::opts_chunk$set(
-  echo = ECHO
-)
-```
-
-# Command line arguments
-
-```{r 'command line arguments'}
-str(opt)
-```
-
-# Download and extract reads
-
-```{r 'download and extract reads'}
-# create a directory to store read files
-dir.create('read_files_directory')
-# download and extract reads
-sra_accessions = strsplit(gsub(',', ' ', 'SRA_ACCESSION'), ' ')[[1]]
-sra_accessions = sra_accessions[sra_accessions != '']
-# loop through SRA accessions to download and extract reads.
-for(id in sra_accessions) {
-  if (SRA_BOOLEAN) {
-    
-    # build URL from SRA accession
-    url = paste0('ftp://ftp.ncbi.nlm.nih.gov/sra/sra-instant/reads/ByRun/sra/',
-                 substr(id, 1, 3), '/',
-                 substr(id, 1, 6), '/', id, '/', id, '.sra')
-    # download sra file with bdss
-    bdss_command = paste0('/tool_deps/_conda/bin/bdss transfer -u ', url)
-    system(bdss_command, intern = TRUE)
-    # convert .sra to .fastq/.fasta
-    if('FORMAT' == 'fasta') {
-      command = paste0('fastq-dump --fasta --split-files ', '-O read_files_directory ', id)
-    } else {
-      command = paste0('fastq-dump --split-files ', '-O read_files_directory ', id)
-    }
-    # command line stdout
-    system(command = command, intern = TRUE)
-  } else  {
-    # if SRA_BOOLEAN is FALSE, download fastq directly
-    # build URL for downloading fastq
-    url_base = paste0('ftp://ftp.sra.ebi.ac.uk/vol1/fastq/',
-                      substr(id, 1, 6), '/', id)
-    # list all fastq files
-    all_fastq_files = strsplit(getURL(url_base, dirlistonly = TRUE), split = '\n')[[1]]
-    if (length(all_fastq_files) == 1) {
-      # this is a single end SRA file. build url to download fastq
-      print(paste0('only one fastq file found for this SRA accession: ', id))
-      print(paste0('Downloading skipped for ', id))
-      # url = paste0(url_base, '/', all_fastq_files)
-      # bdss_command = paste0('/tool_deps/_conda/bin/bdss transfer -u ', url)
-      # run_bdss = system(bdss_command, intern = TRUE)
-      # print(run_bdss)
-    } else {
-      print(paste0('Two fastq files found for this SRA accession: ', id))
-      url_1 = paste0(url_base, '/', all_fastq_files[1])
-      bdss_command_1 = paste0('/tool_deps/_conda/bin/bdss transfer -u ', url_1)
-      run_bdss_1 = system(bdss_command_1, intern = TRUE)
-      print(run_bdss_1)
-      url_2 = paste0(url_base, '/', all_fastq_files[1])
-      bdss_command_2 = paste0('/tool_deps/_conda/bin/bdss transfer -u ', url_2)
-      run_bdss_2 = system(bdss_command_2, intern = TRUE)
-      print(run_bdss_2)
-    }
-  }
-
-}
-# remove all .sra file
-system('rm *.sra', intern = TRUE)
-```
-
-
-# Rename files
-
-```{r}
-old_files = paste0('./read_files_directory/', list.files('./read_files_directory'))
-new_files = gsub('_1', '_forward', old_files)
-new_files = gsub('_2', '_reverse', new_files)
-file.rename(old_files, new_files)
-```
-
--- a/bdss_client_sra_pe.xml	Sat Oct 14 17:15:39 2017 -0400
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,58 +0,0 @@
-<tool id="rmarkdown_bdss_client_sra_pe" name="BDSS client SRA PE" version="1.0.1">
-    <requirements>
-        <requirement type="package" version="1.15.0.6-0">pandoc</requirement>
-        <requirement type="package" version="3.3.2">r-base</requirement>
-        <requirement type="package" version="1.20.0">r-getopt</requirement>
-        <requirement type="package" version="1.2">r-rmarkdown</requirement>
-        <requirement type="package" version="0.3.5">r-htmltools</requirement>
-        <requirement type="package" version="0.5.0">r-dplyr</requirement>
-        <requirement type="package" version="0.5.4">parallel-fastq-dump</requirement>
-        <requirement type="package" version="1.95_4.8">r-rcurl</requirement>
-    </requirements>
-    <description>
-        Download and extract paired end reads in fastq or fasta format from NCBI SRA. The output is a list of paired
-        datasets
-        collection.
-    </description>
-    <stdio>
-        <!--All stderr are redirected to a file. "XXX" is used to match with nothing-->
-        <regex match="XXX"
-               source="stderr"
-               level="warning"
-               description="Check the warnings_and_errors.txt file for more details."/>
-    </stdio>
-    <command>
-        <![CDATA[
-            Rscript '${__tool_directory__}/bdss_client_sra_pe_render.R'
-                -i '$sra_accession'
-                -e $echo
-                -f $format
-                -S $sra
-
-                -r $report
-                -d $report.files_path
-                -s $sink_message
-
-                -t '${__tool_directory__}/bdss_client_sra_pe.Rmd'
-        ]]>
-    </command>
-    <inputs>
-        <param type="text" name="sra_accession" label="SRR/DRR/ERR accessions" optional="false"
-               help="A list of SRR/DRR/ERR accessions separated by comma or space. e.g. SRR6077558,ERR343809"/>
-        <param type="boolean" name="format" truevalue="fastq" falsevalue="fasta" checked="true"
-               label="output files in fastq (Yes) or fasta (No)?"/>
-        <param type="boolean" name="sra" truevalue="TRUE" falsevalue="FALSE" checked="true"
-               label="Download SRA or Fastq"/>
-        <param type="boolean" name="echo" truevalue="TRUE" falsevalue="FALSE" checked="false"
-               label="Display analysis code in report?"/>
-    </inputs>
-    <outputs>
-        <data format="html" name="report" label="BDSS report"/>
-        <collection type="list:paired" name="list_collection" label="BDSS fastq/fasta (paired end reads)">
-            <discover_datasets
-                    pattern="(?P&lt;identifier_0&gt;[^_]+)_(?P&lt;identifier_1&gt;[^_]+)\.(?P&lt;ext&gt;[^\._]+)?"
-                    directory="read_files_directory"/>
-        </collection>
-        <data format="txt" name="sink_message" label="Warnings and Errors" from_work_dir="warnings_and_errors.txt"/>
-    </outputs>
-</tool>
\ No newline at end of file
--- a/bdss_client_sra_pe_render.R	Sat Oct 14 17:15:39 2017 -0400
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,90 +0,0 @@
-library(getopt)
-library(rmarkdown)
-library(htmltools)
-library(dplyr)
-library(RCurl)
-
-
-##============ Sink warnings and errors to a file ==============
-## use the sink() function to wrap all code within it.
-##==============================================================
-zz = file('warnings_and_errors.txt')
-sink(zz)
-sink(zz, type = 'message')
-##---------below is the code for rendering .Rmd templates-----
-
-  ##=============STEP 1: handle command line arguments==========
-  ##
-  ##============================================================
-  # column 1: the long flag name
-  # column 2: the short flag alias. A SINGLE character string
-  # column 3: argument mask
-  #           0: no argument
-  #           1: argument required
-  #           2: argument is optional
-  # column 4: date type to which the flag's argument shall be cast.
-  #           possible values: logical, integer, double, complex, character.
-  #-------------------------------------------------------------
-  #++++++++++++++++++++ Best practice ++++++++++++++++++++++++++
-  # 1. short flag alias should match the flag in the command section in the XML file.
-  # 2. long flag name can be any legal R variable names
-  # 3. two names in args_list can have common string but one name should not be a part of another name.
-  #    for example, one name is "ECHO", if another name is "ECHO_XXX", it will cause problems.
-  #+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
-  ##------- 1. input data ---------------------
-  args_list=list()
-  args_list$SRA_ACCESSION = c('sra_accession', 'i', '1', 'character')
-  args_list$FORMAT = c('format', 'f', '1', 'character')
-  args_list$SRA_BOOLEAN = c('sra_boolean', 'S', '1', 'character')
-  args_list$ECHO = c('echo', 'e', '1', 'character')
-  ##--------2. output report and outputs --------------
-  args_list$REPORT_HTML = c('report_html', 'r', '1', 'character')
-  args_list$REPORT_DIR = c('report_dir', 'd', '1', 'character')
-  args_list$SINK_OUTPUT = c('sink_message', 's', '1', 'character')
-  ##--------3. Rmd templates in the tool directory ----------
-  args_list$bdss_client_sra_se_RMD = c('bdss_client_sra_se_rmd', 't', '1', 'character')
-  
-  opt = getopt(t(as.data.frame(args_list)))
-  
-  
-  ##=======STEP 2: create report directory (optional)==========
-  ##
-  ##===========================================================
-  dir.create(opt$report_dir)
-  
-  ##=STEP 3: replace placeholders in .Rmd with argument values=
-  ##
-  ##===========================================================
-  #++ need to replace placeholders with args values one by one+
-  #----- 01 bdss_client_sra_se.Rmd -----------------------
-  readLines(opt$bdss_client_sra_se_rmd) %>%
-    (function(x) {
-      gsub('SRA_ACCESSION', opt$sra_accession, x)
-    }) %>%
-    (function(x) {
-      gsub('FORMAT', opt$format, x)
-    }) %>%
-    (function(x) {
-      gsub('SRA_BOOLEAN', opt$sra_boolean, x)
-    }) %>%
-    (function(x) {
-      gsub('ECHO', opt$echo, x)
-    }) %>%
-    (function(x) {
-      gsub('REPORT_DIR', opt$report_dir, x)
-    }) %>%
-    (function(x) {
-      fileConn = file('bdss_client_sra_se.Rmd')
-      writeLines(x, con=fileConn)
-      close(fileConn)
-    })
-  
-  ##=============STEP 4: render .Rmd templates=================
-  ##
-  ##===========================================================
-  render('bdss_client_sra_se.Rmd', output_file = opt$report_html)
-
-
-##--------end of code rendering .Rmd templates----------------
-sink()
-##=========== End of sinking output=============================
\ No newline at end of file
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/bdss_client_sra_render.R	Sat Oct 14 19:54:57 2017 -0400
@@ -0,0 +1,89 @@
+library(getopt)
+library(rmarkdown)
+library(htmltools)
+library(dplyr)
+library(RCurl)
+
+
+##============ Sink warnings and errors to a file ==============
+## use the sink() function to wrap all code within it.
+##==============================================================
+zz = file('warnings_and_errors.txt')
+sink(zz)
+sink(zz, type = 'message')
+##---------below is the code for rendering .Rmd templates-----
+
+##=============STEP 1: handle command line arguments==========
+##
+##============================================================
+# column 1: the long flag name
+# column 2: the short flag alias. A SINGLE character string
+# column 3: argument mask
+#           0: no argument
+#           1: argument required
+#           2: argument is optional
+# column 4: date type to which the flag's argument shall be cast.
+#           possible values: logical, integer, double, complex, character.
+#-------------------------------------------------------------
+#++++++++++++++++++++ Best practice ++++++++++++++++++++++++++
+# 1. short flag alias should match the flag in the command section in the XML file.
+# 2. long flag name can be any legal R variable names
+# 3. two names in args_list can have common string but one name should not be a part of another name.
+#    for example, one name is "ECHO", if another name is "ECHO_XXX", it will cause problems.
+#+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
+##------- 1. input data ---------------------
+args_list=list()
+args_list$SRA_IDS_SE = c('sra_ids_se', 'i', '1', 'character')
+args_list$SRA_IDS_PE = c('sra_ids_pe', 'i', '1', 'character')
+args_list$ECHO = c('echo', 'e', '1', 'character')
+##--------2. output report and outputs --------------
+args_list$REPORT_HTML = c('report_html', 'r', '1', 'character')
+args_list$REPORT_DIR = c('report_dir', 'd', '1', 'character')
+args_list$SINK_OUTPUT = c('sink_message', 's', '1', 'character')
+##--------3. Rmd templates in the tool directory ----------
+args_list$BDSS_CLIENT_RMD = c('bdss_client_rmd', 't', '1', 'character')
+
+opt = getopt(t(as.data.frame(args_list)))
+
+
+##=======STEP 2: create report directory (optional)==========
+##
+##===========================================================
+dir.create(opt$report_dir)
+
+##=STEP 3: replace placeholders in .Rmd with argument values=
+##
+##===========================================================
+#++ need to replace placeholders with args values one by one+
+#----- 01 bdss_client.Rmd -----------------------
+readLines(opt$bdss_client_rmd) %>%
+  (function(x) {
+    gsub('SRA_IDS_SE', opt$sra_ids_se, x)
+  }) %>%
+  (function(x) {
+    gsub('SRA_IDS_PE', opt$sra_ids_pe, x)
+  }) %>%
+  (function(x) {
+    gsub('FORMAT', opt$format, x)
+  }) %>%
+  (function(x) {
+    gsub('ECHO', opt$echo, x)
+  }) %>%
+  (function(x) {
+    gsub('REPORT_DIR', opt$report_dir, x)
+  }) %>%
+  (function(x) {
+    fileConn = file('bdss_client.Rmd')
+    writeLines(x, con=fileConn)
+    close(fileConn)
+  })
+
+##=============STEP 4: render .Rmd templates=================
+##
+##===========================================================
+render('bdss_client.Rmd', output_file = opt$report_html)
+
+
+##--------end of code rendering .Rmd templates----------------
+sink()
+##=========== End of sinking output=============================
\ No newline at end of file
--- a/bdss_client_sra_se.Rmd	Sat Oct 14 17:15:39 2017 -0400
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,98 +0,0 @@
----
-title: 'Download and extract single end fastq/fasta data with BDSS client from SRA accessions'
-output:
-    html_document:
-      number_sections: true
-      toc: true
-      theme: cosmo
-      highlight: tango
----
-
-```{r setup, include=FALSE, warning=FALSE, message=FALSE}
-knitr::opts_chunk$set(
-  echo = ECHO
-)
-```
-
-# Command line arguments
-
-```{r 'command line arguments'}
-str(opt)
-```
-
-# BDSS configuration file
-
-First, we create a bdss configuration file `bdss.cfg` in the current directory.
-
-```{r}
-system('echo "[metadata_repository]" > bdss.cfg')
-system('echo url=http://bdss.bioinfo.wsu.edu/ >> bdss.cfg')
-```
-
-# Download and extract reads
-
-```{r 'download and extract reads'}
-# create a directory to store read files
-dir.create('read_files_directory')
-# download and extract reads
-sra_accessions = strsplit(gsub(',', ' ', 'SRA_ACCESSION'), ' ')[[1]]
-sra_accessions = sra_accessions[sra_accessions != '']
-# loop through SRA accessions to download and extract reads.
-for(id in sra_accessions) {
-  ## if SRA_BOOLEAN is TRUE, download .sra file and then convert it to fastq/fasta
-  if (SRA_BOOLEAN) {
-    # build URL from SRA accession
-    url = paste0('ftp://ftp.ncbi.nlm.nih.gov/sra/sra-instant/reads/ByRun/sra/',
-                 substr(id, 1, 3), '/',
-                 substr(id, 1, 6), '/', id, '/', id, '.sra')
-    # download sra file with bdss
-    bdss_command = paste0('/tool_deps/_conda/bin/bdss transfer -u ', url)
-    system(bdss_command, intern = TRUE)
-    # convert .sra to .fastq/.fasta
-    if('FORMAT' == 'fasta') {
-      command = paste0('fastq-dump --fasta ', '-O read_files_directory ', id)
-    } else {
-      command = paste0('fastq-dump ', '-O read_files_directory ', id)
-    }
-  } else {
-    # if SRA_BOOLEAN is FALSE, download fastq directly
-    # build URL for downloading fastq
-    url_base = paste0('ftp://ftp.sra.ebi.ac.uk/vol1/fastq/',
-                      substr(id, 1, 6), '/', id)
-    # list all fastq files
-    all_fastq_files = strsplit(getURL(url_base, dirlistonly = TRUE), split = '\n')[[1]]
-    if (length(all_fastq_files) == 1) {
-      # this is a single end SRA file. build url to download fastq
-      url = paste0(url_base, '/', all_fastq_files)
-      bdss_command = paste0('/tool_deps/_conda/bin/bdss transfer -u ', url)
-      run_bdss = system(bdss_command, intern = TRUE)
-      print(run_bdss)
-    } else {
-      print(paste0('Two fastq files found for this SRA accession: ', id))
-      print('Downloading skipped for ', id)
-      # url_1 = paste0(url_base, '/', all_fastq_files[1])
-      # bdss_command_1 = paste0('/tool_deps/_conda/bin/bdss transfer -u ', url_1)
-      # run_bdss_1 = system(bdss_command, intern = TRUE)
-      # url_2 = paste0(url_base, '/', all_fastq_files[1])
-      # bdss_command_2 = paste0('/tool_deps/_conda/bin/bdss transfer -u ', url_2)
-      # run_bdss_2 = system(bdss_command, intern = TRUE)
-    }
-  }
-  
-}
-
-# remove all .sra file
-system('rm *.sra', intern = TRUE)
-```
-
-* `fastq-dump` command
-```{r}
-print(command)
-```
-
-* `command line stdout`
-
-```{r}
-system(command = command, intern = TRUE)
-```
-
--- a/bdss_client_sra_se.xml	Sat Oct 14 17:15:39 2017 -0400
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,55 +0,0 @@
-<tool id="rmarkdown_bdss_client_sra_se" name="BDSS client SRA SE" version="1.0.1">
-    <requirements>
-        <requirement type="package" version="1.15.0.6-0">pandoc</requirement>
-        <requirement type="package" version="3.3.2">r-base</requirement>
-        <requirement type="package" version="1.20.0">r-getopt</requirement>
-        <requirement type="package" version="1.2">r-rmarkdown</requirement>
-        <requirement type="package" version="0.3.5">r-htmltools</requirement>
-        <requirement type="package" version="0.5.0">r-dplyr</requirement>
-        <requirement type="package" version="0.5.4">parallel-fastq-dump</requirement>
-        <requirement type="package" version="1.95_4.8">r-rcurl</requirement>
-    </requirements>
-    <description>
-        Download and extract single end reads in fastq or fasta format from NCBI SRA. The output is a list of datasets
-        collection.
-    </description>
-    <stdio>
-        <!--All stderr are redirected to a file. "XXX" is used to match with nothing-->
-        <regex match="XXX"
-               source="stderr"
-               level="warning"
-               description="Check the warnings_and_errors.txt file for more details."/>
-    </stdio>
-    <command>
-        <![CDATA[
-            Rscript '${__tool_directory__}/bdss_client_sra_se_render.R'
-                -i '$sra_accession'
-                -e $echo
-                -f $format
-                -S $sra
-
-                -r $report
-                -d $report.files_path
-                -s $sink_message
-
-                -t '${__tool_directory__}/bdss_client_sra_se.Rmd'
-        ]]>
-    </command>
-    <inputs>
-        <param type="text" name="sra_accession" label="SRR/DRR/ERR accessions"
-               help="A list of SRR/DRR/ERR accessions separated by comma or space. e.g. SRR6077558,ERR343809"/>
-        <param type="boolean" name="format" truevalue="fastq" falsevalue="fasta" checked="true"
-               label="output files in fastq (Yes) or fasta (No)?"/>
-        <param type="boolean" name="sra" truevalue="TRUE" falsevalue="FALSE" checked="true"
-               label="Download SRA or Fastq"/>
-        <param type="boolean" name="echo" truevalue="TRUE" falsevalue="FALSE" checked="false"
-               label="Display analysis code in report?"/>
-    </inputs>
-    <outputs>
-        <data format="html" name="report" label="BDSS report"/>
-        <collection type="list" name="list_collection" label="BDSS fastq/fasta (single end reads)">
-            <discover_datasets pattern="__name_and_ext__" directory="read_files_directory"/>
-        </collection>
-        <data format="txt" name="sink_message" label="Warnings and Errors" from_work_dir="warnings_and_errors.txt"/>
-    </outputs>
-</tool>
\ No newline at end of file
--- a/bdss_client_sra_se_render.R	Sat Oct 14 17:15:39 2017 -0400
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,90 +0,0 @@
-library(getopt)
-library(rmarkdown)
-library(htmltools)
-library(dplyr)
-library(RCurl)
-
-
-##============ Sink warnings and errors to a file ==============
-## use the sink() function to wrap all code within it.
-##==============================================================
-zz = file('warnings_and_errors.txt')
-sink(zz)
-sink(zz, type = 'message')
-##---------below is the code for rendering .Rmd templates-----
-
-  ##=============STEP 1: handle command line arguments==========
-  ##
-  ##============================================================
-  # column 1: the long flag name
-  # column 2: the short flag alias. A SINGLE character string
-  # column 3: argument mask
-  #           0: no argument
-  #           1: argument required
-  #           2: argument is optional
-  # column 4: date type to which the flag's argument shall be cast.
-  #           possible values: logical, integer, double, complex, character.
-  #-------------------------------------------------------------
-  #++++++++++++++++++++ Best practice ++++++++++++++++++++++++++
-  # 1. short flag alias should match the flag in the command section in the XML file.
-  # 2. long flag name can be any legal R variable names
-  # 3. two names in args_list can have common string but one name should not be a part of another name.
-  #    for example, one name is "ECHO", if another name is "ECHO_XXX", it will cause problems.
-  #+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
-  ##------- 1. input data ---------------------
-  args_list=list()
-  args_list$SRA_ACCESSION = c('sra_accession', 'i', '1', 'character')
-  args_list$FORMAT = c('format', 'f', '1', 'character')
-  args_list$SRA_BOOLEAN = c('sra_boolean', 'S', '1', 'character')
-  args_list$ECHO = c('echo', 'e', '1', 'character')
-  ##--------2. output report and outputs --------------
-  args_list$REPORT_HTML = c('report_html', 'r', '1', 'character')
-  args_list$REPORT_DIR = c('report_dir', 'd', '1', 'character')
-  args_list$SINK_OUTPUT = c('sink_message', 's', '1', 'character')
-  ##--------3. Rmd templates in the tool directory ----------
-  args_list$bdss_client_sra_se_RMD = c('bdss_client_sra_se_rmd', 't', '1', 'character')
-  
-  opt = getopt(t(as.data.frame(args_list)))
-  
-  
-  ##=======STEP 2: create report directory (optional)==========
-  ##
-  ##===========================================================
-  dir.create(opt$report_dir)
-  
-  ##=STEP 3: replace placeholders in .Rmd with argument values=
-  ##
-  ##===========================================================
-  #++ need to replace placeholders with args values one by one+
-  #----- 01 bdss_client_sra_se.Rmd -----------------------
-  readLines(opt$bdss_client_sra_se_rmd) %>%
-    (function(x) {
-      gsub('SRA_ACCESSION', opt$sra_accession, x)
-    }) %>%
-    (function(x) {
-      gsub('FORMAT', opt$format, x)
-    }) %>%
-    (function(x) {
-      gsub('SRA_BOOLEAN', opt$sra_boolean, x)
-    }) %>%
-    (function(x) {
-      gsub('ECHO', opt$echo, x)
-    }) %>%
-    (function(x) {
-      gsub('REPORT_DIR', opt$report_dir, x)
-    }) %>%
-    (function(x) {
-      fileConn = file('bdss_client_sra_se.Rmd')
-      writeLines(x, con=fileConn)
-      close(fileConn)
-    })
-  
-  ##=============STEP 4: render .Rmd templates=================
-  ##
-  ##===========================================================
-  render('bdss_client_sra_se.Rmd', output_file = opt$report_html)
-  
-
-##--------end of code rendering .Rmd templates----------------
-sink()
-##=========== End of sinking output=============================
\ No newline at end of file